LLM的长文本处理为何频频“走神”？MuDAF给出了新答案。 查-20250221074023

[CL]《MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads》W Liu, N Wu, S Yang, W Ding... [Microsoft] (2025) 网页链接 #机器学习##人工智能##论文##AI创造营#